Firehose

17 SEP 2026 · Paper

JEPA-Anything: Learning Predictive Models across Different Worlds

This paper develops a new framework, JEPA-Anything, that enables predictive models to work across different domains and systems, allowing for world modeling and learning from interaction. Practitioners might care about this because it could lead to more generalizable and versatile AI models.

world modeling domain-agnostic predictive factorization orthogonal predictive factorization joint-embedding architectures continual learning

Browse by tag

JEPA-Anything: Learning Predictive Models across Different Worlds